© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38614
    Prev
    Next
    INDEX
    Explanations

    diseases and data transmission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦæĸ¹å¼ıæĿ¥
    -0.11
    å°±å¤ŁäºĨ
    -0.09
    æĸ°ä¸ī
    -0.09
    æĪijä¸įçŁ¥éģĵ
    -0.09
    ore
    -0.09
    ä¸įéĶĻçļĦ
    -0.09
     ÑģвоиÑħ
    -0.09
    ä¸Ģç³»åĪĹ
    -0.08
    hort
    -0.08
    æĥ³åĬŀæ³ķ
    -0.08
    POSITIVE LOGITS
    èĻ½
    0.12
    åĽºçĦ¶
    0.12
    ä¹Łå¥½
    0.11
    ä¹ŁåĽłæѤ
    0.10
    è°ĥæŁ¥æĺ¾ç¤º
    0.10
    èĻ½çĦ¶
    0.10
    è¿Ļæīį
    0.10
     ведÑĮ
    0.10
    è¿Ļ个è¯į
    0.10
    åij¼
    0.09
    Activations Density 1.353%

    No Known Activations